A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
Computer vision, as a part of machine learning, gains significant attention from researches nowadays. Aerial scene classification is a prominent chapter of computer vision with a vast application: military, surveillance and security, environment monitoring, detection of geospatial objects, etc. There are several publicly available remote sensing image datasets, which enable the deployment of various aerial scene classification algorithms. In our article, we use transfer learning fromdoi:10.31449/inf.v45i3.3296 fatcat:xns4uecolrfbjex4aw4dlf23eu
more »... deep Convolutional Neural Networks (CNN) within remote sensing image classification. Neural networks utilized in our research are high-dimensional previously trained CNN on ImageNet dataset. Transfer learning can be performed through feature extraction or fine-tuning. We proposed a two-stream feature extraction method and afterward image classification through a handcrafted classifier. Fine-tuning was performed with adaptive learning rates and a regularization method label smoothing. The proposed transfer learning techniques were validated on two remote sensing image datasets: WHU RS datasets and AID dataset. Our proposed method obtained competitive results compared to state-of-the-art methods. Povzetek: Metoda prenesenega učenja je uporabljena za analizo posnetkov iz zraka na nekaj referenčnih bazah.
Advances in Intelligent Systems and Computing
The cloud computing application for water resources modeling and optimization based on open source software is a continuation of a previous research presented in  . This article presents further research that is focused on distributing the web application on two separate virtual machines (VM) and upgrading it to a cloud computing application. The cloud application was deployed and tested in a distributed computer environment running on two virtual machines (VM-1 and VM-2). The application isdoi:10.1007/978-3-319-25733-4_8 fatcat:3dtp62u3ubhrdliogwpqiep7ly
more »... upgraded with an additional web service for user management, while still having the previous three services for: (1) support for water resources modelling (2) spatial data infrastructure (SDI) and (3) water resources optimization, as reported in  from the previous research. The web services for support of water resources modelling and user management are deployed on VM-1 while the SDI and water resources optimization web services are deployed on VM-2. The web services communicate with web feature service transactional (WFS-T), which is an XML asynchronous messaging protocol. This research demonstrates the capability to scale and distribute the cloud application between several VMs. The article discusses the main cloud application capabilities and its future upgrades.
Authors' Profiles Mirjana Kocaleva received a Master degree in Information Systems, Department of Information Technology at Faculty of Computer Science at University "Goce Delcev" -Stip, Macedonia in 2014 ...doi:10.5815/ijmecs.2015.04.03 fatcat:wejpsnrdnnd4zblmw7d7ksbrgy
The chaotic systems are already known in the theory of chaos. In our paper will be analyzed the following chaotic systems: Rossler, Chua and Chen systems. All of them are systems of ordinary differential equations. By mathematical software Mathematica and MatLab, their graphical representation as continuous dynamical systems is already known. By computer simulations, via examples, the systems will be analyzed using AnyLogic software. We would like to present the way how ordinary differentialdoi:10.18421/tem72-31 fatcat:3dwrvri4vvcknkz6bqma3j2vfa
more »... ations are modeling with AnyLogic software, as one of the simplest software for use.
Development of information technologies is growing steadily. With the latest software technologies development and application of the methods of artificial intelligence and machine learning intelligence embededs in computers, the expectations are that in near future computers will be able to solve problems themselves like people do. Artificial intelligence emulates human behavior on computers. Rather than executing instructions one by one, as theyare programmed, machine learning employs priordoi:10.18421/tem52-18 fatcat:hb6ymdo5jrhbdkn2hfwe3bk5bi